What is Yetibrowser Mcp?
Yetibrowser Mcp is a fully open-source implementation of the Browser MCP workflow. It links a Node-based MCP server with Chrome/Firefox extensions so Model Context Protocol clients—such as Codex/Claude Code, Cursor, Windsurf, MCP Inspector, or custom tools—can automate a real browser tab while keeping every byte on the user’s machine and fully auditable.
How to use Yetibrowser Mcp?
Install the browser extension (Chrome from the Chrome Web Store; Firefox is not yet available). Then start the MCP server with npx yetibrowser-mcp (optionally with --ws-port <port> to pin a specific WebSocket port). Configure your MCP client to run that command. For Codex CLI, edit ~/.codex/config.toml with args = ["yetibrowser-mcp"]. For Claude Code, add the server entry to ~/Library/Application Support/Claude/claude_desktop_config.json. Once the extension connects to a tab, the tools become available.
Key features of Yetibrowser Mcp
- Transparent and hackable – no blob downloads; inspect, fork, and extend every component.
- Local-first – extension only talks to a localhost MCP server; browsing data never leaves your device.
- Cross-browser – shared logic powers both Chrome and Firefox packages (Firefox build pending fuller MV3 support).
- Developer-focused tooling – richer console capture, DOM diffing, page-state dumps, and full-page screenshots.
- Production-friendly – scripts and docs for packaging, publishing, and integrating with IDE workflows.
Use cases of Yetibrowser Mcp
- AI-assisted web automation for debugging and QA tasks.
- Automated form filling and navigation testing via MCP clients.
- Capturing accessibility-oriented snapshots and diffing DOM changes.
- Gathering page state (forms, storage, cookies) and console logs for troubleshooting.
- Integrating browser control into custom MCP-aware tools or IDEs.
评论